MCP Reference

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations include destructiveHint=true and readOnlyHint=false, but the description adds no context about side effects, especially for 'unload' which likely has destructive consequences. The phrase 'Unload request result' is vague and does not disclose what unloading entails or any irreversible actions. The description neither contradicts the annotations nor enriches them, leaving the destructive behavior unexplained.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a compact list of three action-example pairs, but each line repeats the tool name and invocation pattern (e.g., 'mcp.mcp(action=..., payload=...)'), which is redundant. The structure is not front-loaded with a clear overall purpose; the key information is distributed across lines. It is concise in word count but could be better organized with a summary line first and examples as illustrations.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a metadata/discovery tool with three distinct operations and no output schema, the description is thin. It does not explain what 'list_by_category' returns, how the 'format' parameter affects output, or what an 'unload request result' looks like. The relationship to sibling tools like mcp.help is unaddressed, and the destructive nature of unload is not elaborated. Given the tool's complexity, the description is incomplete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% for parameters, and the description adds concrete examples for payload structures (e.g., 'payload={"keywords":["collection"],"limit":5}') for search_tools, and shows the format of unload's payload. These examples clarify parameter syntax and expected shapes beyond the schema's generic descriptions. The action enum is semantically mapped to each example, aiding correct invocation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly enumerates three distinct actions (search_tools, list_by_category, unload) with brief functional tags ('Filtered tool/action catalog matches', 'Tool categories listing', 'Unload request result'). It distinguishes actions from each other, though it lacks a single overarching statement like 'Tool discovery and metadata' which only appears in the schema description. The resource is the mcp tool catalog, and verbs are search/list/unload.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage contexts for each action (e.g., 'search_tools' for finding tools by keywords, 'list_by_category' for listing categories, 'unload' for unloading tools), but it does not explicitly state when to use this tool versus alternatives like mcp.help or when not to use it. No exclusions or alternative tool references are provided, so guidance is only implicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.